https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/Head https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://www.nanopub.org/nschema#hasAssertion https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/assertion https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://www.nanopub.org/nschema#hasProvenance https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/provenance https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://www.nanopub.org/nschema#hasPublicationInfo https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/pubinfo https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.nanopub.org/nschema#Nanopublication https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/assertion https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/dc/terms/title KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/describes https://neverblink.eu/ontologies/llm-kg/methods#KGo1 https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4o https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4oMini https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#DeepSeekR1 https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#GRPO https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#Gemini20FlashThinking https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#O1Mini https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#OpenO1 https://doi.org/10.48550/arXiv.2508.15790 http://purl.org/spar/cito/discusses https://neverblink.eu/ontologies/llm-kg/methods#QwQ32BPreview https://doi.org/10.48550/arXiv.2508.15790 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://www.w3.org/ns/prov#Entity https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4o http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4o http://www.w3.org/2000/01/rdf-schema#comment ChatGPT-4o is an advanced general-purpose large language model (GPLLM) used in two contexts: first, as a tool to generate multi-hop questions for the KG-MHQA SFT dataset creation, and second, as a powerful baseline for performance comparison in the experiments. https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4o http://www.w3.org/2000/01/rdf-schema#label ChatGPT-4o https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4oMini http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4oMini http://www.w3.org/2000/01/rdf-schema#comment ChatGPT4o-mini is an advanced general-purpose large language model (GPLLM) used as a baseline model for comparative evaluation against the proposed KG-o1 models on multi-hop reasoning tasks. https://neverblink.eu/ontologies/llm-kg/methods#ChatGPT4oMini http://www.w3.org/2000/01/rdf-schema#label ChatGPT4o-mini https://neverblink.eu/ontologies/llm-kg/methods#DeepSeekR1 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#DeepSeekR1 http://www.w3.org/2000/01/rdf-schema#comment DeepSeek-R1 is a specific large reasoning model (LRM) used as a strong baseline for evaluating the performance of KG-o1 models on multi-hop question answering datasets. https://neverblink.eu/ontologies/llm-kg/methods#DeepSeekR1 http://www.w3.org/2000/01/rdf-schema#label DeepSeek-R1 https://neverblink.eu/ontologies/llm-kg/methods#GRPO http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#GRPO http://www.w3.org/2000/01/rdf-schema#comment GRPO is a reinforcement learning method that serves as a comparative baseline in the ablation studies, where its performance in boosting LLMs' multi-hop reasoning is contrasted with other fine-tuning and optimization strategies, including the paper's Self-improved Adaptive DPO. https://neverblink.eu/ontologies/llm-kg/methods#GRPO http://www.w3.org/2000/01/rdf-schema#label GRPO https://neverblink.eu/ontologies/llm-kg/methods#Gemini20FlashThinking http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#Gemini20FlashThinking http://www.w3.org/2000/01/rdf-schema#comment Gemini 2.0 Flash Thinking is a specific large reasoning model (LRM) used as a strong baseline for evaluating the performance of KG-o1 models on multi-hop question answering tasks, highlighting its advanced reasoning capabilities. https://neverblink.eu/ontologies/llm-kg/methods#Gemini20FlashThinking http://www.w3.org/2000/01/rdf-schema#label Gemini 2.0 Flash Thinking https://neverblink.eu/ontologies/llm-kg/methods#KGo1 http://purl.org/dc/terms/subject https://neverblink.eu/ontologies/llm-kg/categories#KGEnhancedLLMPretraining https://neverblink.eu/ontologies/llm-kg/methods#KGo1 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#KGo1 http://www.w3.org/2000/01/rdf-schema#comment KG-o1 is a novel four-stage framework that integrates Knowledge Graphs (KGs) to enhance Large Language Models' (LLMs) multi-hop reasoning abilities. It involves constructing KG-derived datasets (KG-MHQA SFT and DPO) and using them to fine-tune LLMs (via Supervised Fine-Tuning and a "Self-improved Adaptive DPO" strategy), aiming to improve the LLM's intrinsic knowledge expression and reasoning capabilities during a training stage by internalizing logical paths. https://neverblink.eu/ontologies/llm-kg/methods#KGo1 http://www.w3.org/2000/01/rdf-schema#label KG-o1 https://neverblink.eu/ontologies/llm-kg/methods#KGo1 https://neverblink.eu/ontologies/llm-kg/hasTopCategory https://neverblink.eu/ontologies/llm-kg/top-categories#KGEnhancedLLM https://neverblink.eu/ontologies/llm-kg/methods#O1Mini http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#O1Mini http://www.w3.org/2000/01/rdf-schema#comment o1-mini is a specific large reasoning model (LRM) mentioned as a prominent baseline for comparison against the proposed KG-o1 models in multi-hop question answering tasks. https://neverblink.eu/ontologies/llm-kg/methods#O1Mini http://www.w3.org/2000/01/rdf-schema#label o1-mini https://neverblink.eu/ontologies/llm-kg/methods#OpenO1 http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#OpenO1 http://www.w3.org/2000/01/rdf-schema#comment Open-o1 is a specific influential large reasoning model (LRM) from the open-source community, used as a baseline for performance comparison in the experiments of the paper. https://neverblink.eu/ontologies/llm-kg/methods#OpenO1 http://www.w3.org/2000/01/rdf-schema#label Open-o1 https://neverblink.eu/ontologies/llm-kg/methods#QwQ32BPreview http://www.w3.org/1999/02/22-rdf-syntax-ns#type http://purl.org/spar/fabio/Workflow https://neverblink.eu/ontologies/llm-kg/methods#QwQ32BPreview http://www.w3.org/2000/01/rdf-schema#comment QwQ-32B-Preview is a specific large reasoning model (LRM) included as a prominent baseline for comparative experiments against the KG-o1 models on multi-hop reasoning tasks. https://neverblink.eu/ontologies/llm-kg/methods#QwQ32BPreview http://www.w3.org/2000/01/rdf-schema#label QwQ-32B-Preview https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/provenance https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/assertion http://www.w3.org/ns/prov#wasAttributedTo https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/assertion http://www.w3.org/ns/prov#wasDerivedFrom https://doi.org/10.48550/arXiv.2508.15790 https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/pubinfo https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://purl.org/dc/terms/created 2026-03-13T16:10:14.372Z https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://purl.org/dc/terms/creator https://neverblink.eu/ontologies/llm-kg/agent https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://purl.org/nanopub/x/hasNanopubType https://neverblink.eu/ontologies/llm-kg/PaperAssessmentResult https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://purl.org/nanopub/x/supersedes https://w3id.org/np/RAMmlNyKev37Gbg7UWMXcFz7n75r_vyq1giyo4LxPpvI0 https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA http://www.w3.org/2000/01/rdf-schema#label LLM-KG assessment for paper 10.48550/arXiv.2508.15790 https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/sig http://purl.org/nanopub/x/hasAlgorithm RSA https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/sig http://purl.org/nanopub/x/hasPublicKey MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAwNz2QK3SEifno78S7+48zUB0xpTex3mAzW73ZimHqNcdEMU5/apslrGrTHGFAt/Chocgo++r6JQp5ygY7NyJHGWdaIqnt85pjX4PbNfLAvapyUO00qZP34fY61w4eZ9UMtleWEsmZKRtQPyJ8ODl46i/rfPuZlcJGpM9Nmy5mpGWuepqIEvF4a/t7pLVeCEDFSYXT+yaiygt6ynIK5f7TtEDhZpeUf/Q74WhMPJXm4yTU/hqOX4IW+50kWHNArGGZwUaXwzyG6M3Zd6UMModryGkLqS4H/MSE3ZA1Ylnms7BfWLEXhMWlaKi6HRV4nGRDLhxVSi9LSRi3LWKLhNIIQIDAQAB https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/sig http://purl.org/nanopub/x/hasSignature JwesqkdoglWm3/mXA9J8rFpVgW/WxZ4BNq6HnvpmaPwF5MwyNA/dauZGFS67c5xMKrrXdr/AbqsEfPIZ6ZazcmWhu0AVKP/xnFHPbKJXFlS+Pl2jufAYGJ50ZSxXX88mv3L5H9IovO/SjdUo9Wa/VRIc/PlVFgn133b10hOM8YitFc3hRufK/FSce7FdKD4KJauXmPX/g7tTa+Usxcdmse7pm3zeGu8PjS8Ojn+FH6gexIo8BMeZDtWeYlOyAo/GZSq4+IrAbE1JUVz9xU5rVaf7NzCMNwLUvX0jgt8L1yD8E/3N/nvQ7jpLKkt0bWbNM23jQF2XWkiMLGKMFLxnRQ== https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/sig http://purl.org/nanopub/x/hasSignatureTarget https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA https://w3id.org/np/RAQH5ERc1-v6X29eIuWWbwPrx2Kh7lFk9rD2QQklE1WMA/sig http://purl.org/nanopub/x/signedBy https://neverblink.eu/ontologies/llm-kg/agent